EKF based on two FDE schemes for GNSS Vehicle Navigation

Combettes, Christophe; Villien, Christophe

doi:10.1109/vtc2021-spring51267.2021.9448987

Cited by 4 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second approach, named "our approach", exploits the overall feature matrix comprising the two sub-matrices (i.e., the "residual matrix" concatenated with the additional per-link features) as an input to the NN to predict linkwise quality factors, which are then used to compute the weights as in (4) for WLS positioning. Finally, in the third "SOTA" method, the state-of-the-art solution from [26] (see Section 2.3) is used for positioning.…”

Section: Evaluation Resultsmentioning

confidence: 99%

“…In comparison with the previous existing approaches, the method in [26] was shown to significantly improve the positioning performance. This approach was compared with both the well-known GNSS software RTKlib 2.4.2 and the solution delivered by the Ublox receiver.…”

Section: Existing Workmentioning

confidence: 93%

“…The comparison was performed in various operating conditions such as urban, suburban, highways, etc. As shown in Tables 2 and 3, the solution provided by the approach in [26] yielded a better performance with respect to the solution provided by the Ublox chip in filtered mode.…”

Section: Existing Workmentioning

confidence: 93%

“…All the above approaches are standalone and do not have access to previous position estimates. A more-recent solution proposed in [26] relies on a new FDE, which uses a standalone FDE block along with an FDE-based Extended Kalman Filter (EKF). The standalone part of this approach is based on a residual test using WLS.…”

Section: Existing Workmentioning

confidence: 99%

“…Due to the good performance demonstrated by the approach in [26] compared to two representative and well-known approaches, we chose it as a reference benchmark in this paper. As our study is focused on single-epoch localization, we considered only its standalone part.…”

Section: Existing Workmentioning

confidence: 99%

See 4 more Smart Citations

LSTM-Based GNSS Localization Using Satellite Measurement Features Jointly with Pseudorange Residuals

Sbeity,

Villien,

Denis

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

In the Global Navigation Satellite System (GNSS) context, the growing number of available satellites has led to many challenges when it comes to choosing the most-accurate pseudorange contributions, given the strong impact of biased measurements on positioning accuracy, particularly in single-epoch scenarios. This work leverages the potential of machine learning in predicting linkwise measurement quality factors and, hence, optimize measurement weighting. For this purpose, we used a customized matrix composed of heterogeneous features such as conditional pseudorange residuals and per-link satellite metrics (e.g., carrier-to-noise-power-density ratio and its empirical statistics, satellite elevation, carrier phase lock time). This matrix is then fed as an input to a long short-term memory (LSTM) deep neural network capable of exploiting the hidden correlations between these features relevant to positioning, leading to the predictions of efficient measurement weights. Our extensive experimental results on real data, obtained from extensive field measurements, demonstrate the high potential of our proposed solution, which is able to outperform traditional measurement weighting and selection strategies from the state-of-the-art. In addition, we included detailed illustrations based on representative sessions to provide a concrete understanding of the significant gains of our approach, particularly in strongly GNSS-challenged operating conditions.

show abstract

Section: Evaluation Resultsmentioning

confidence: 99%

Section: Existing Workmentioning

confidence: 93%

Section: Existing Workmentioning

confidence: 93%

Section: Existing Workmentioning

confidence: 99%

Section: Existing Workmentioning

confidence: 99%

See 3 more Smart Citations